talk-farley-vibe-coding-best-we-can-do

talk-farley-vibe-coding-best-we-can-do is a skill for Codex from jscraik/Agent-Skills. It costs 194 tokens per session (1,886 once invoked), scanned A, original, Apache-2.0.

A reference guide to Dave Farley's talk about vibe coding, meaning writing software mainly through natural-language instructions to an AI. It argues that clear specifications and repeatable checks are still needed.

In plain words
What is it for?
Use it to discuss programming-language properties, behaviour-driven development, executable specifications, small incremental changes, and automated delivery checks.
Why use it?
Natural language can be unclear and AI-generated code can vary, making it harder to know whether the result matches the intended behaviour.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to discuss programming-language properties, behaviour-driven development, executable specifications, small incremental changes, and automated delivery checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jscraik/agent-skills/talk-farley-vibe-coding-best-we-can-do
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add jscraik/Agent-Skills --skill talk-farley-vibe-coding-best-we-can-do
Clone the repo
git clone --depth 1 https://github.com/jscraik/Agent-Skills

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for talk-farley-vibe-coding-best-we-can-do

README.md
[![agentmods](https://agentmods.dev/badge/skills/jscraik/agent-skills/talk-farley-vibe-coding-best-we-can-do/github.svg)](https://agentmods.dev/skills/jscraik/agent-skills/talk-farley-vibe-coding-best-we-can-do)
Your own site
<a href="https://agentmods.dev/skills/jscraik/agent-skills/talk-farley-vibe-coding-best-we-can-do"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/talk-farley-vibe-coding-best-we-can-do/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for talk-farley-vibe-coding-best-we-can-do

Your own site · 80×15
<a href="https://agentmods.dev/skills/jscraik/agent-skills/talk-farley-vibe-coding-best-we-can-do"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/talk-farley-vibe-coding-best-we-can-do.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 194 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,886 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00194 $0.01886
Opus 5 $0.00097 $0.00943
Sonnet 5 $0.00039 $0.00377
Haiku 4.5 $0.00019 $0.00189

Measured 12d ago against content hash ea9eee0ee12c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

talk-farley-vibe-coding-best-we-can-do scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Plugins/aidevcon/skills/talk-farley-vibe-coding-best-we-can-do/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vibe Coding — Is this really the best we can do? — Dave Farley

Farley argues that "vibe coding" with natural language alone is fundamentally inadequate because natural language lacks the three properties that make programming languages useful: a simple consistent grammar, unambiguous expression of intent, and repeatable deterministic execution. AI coding accelerates the easy part of software development (writing code) while making the hard parts (specifying what we want and verifying we got it) worse, and breaks our ability to work incrementally. His prescription: treat AI assistants like compilers, and prompt them with BDD-style executable specifications written in problem-specific DSLs, verified by deployment pipelines — i.e. continuous delivery practices applied to AI-driven development.

Grounding rules — MUST follow when answering

  1. Before answering any specific question, read outline.md to locate the relevant section, then read that section of transcript.md.
  2. When attributing words, quote short, non-sensitive excerpts from transcript.md. Never put quotation marks around paraphrased content.
  3. If a claim isn't in transcript.md, say "the talk doesn't address this" — do not infer Farley's positions from his other published work or outside knowledge unless the user explicitly asks for it (and mark it clearly as not from this talk).
  4. Cite by transcript line range whenever possible.
  5. Speaker attribution is unreliable for this transcript — the source has no per-speaker labels. The talk has a clear single speaker (Dave Farley) plus an MC making opening and closing remarks. When quoting the MC's housekeeping (rail strikes, party, ratings), say so; do not attribute MC remarks to Farley.
  6. Cross-reference any named addressee with the participants list in the transcript header / outline.md before attributing.

Default workflow (applies to all use cases below)

Every response should follow this shared pattern unless a specific use case adds extra steps:

Read the full file on GitHub · 139 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 139 lines · 194 tokens per session scan A ea9eee0ee12c

Subscribe to this mod's changes

talk-farley-vibe-coding-best-we-can-do is a skill published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 11d ago), licensed Apache-2.0. It adds 194 tokens to every session and 1,886 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories